Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SERP analysis techniques for intent classification, feature identification, and competitive intelligence. Use when analyzing search results for content strategy.
.claude/skills/nicepkg-serp-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -78% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -37% | 0% |
| case-14 | ✓→✗ | ▼ Worse | -50% | 0% |
| Intent | SERP Signals | User Goal | Content Format | |--------|--------------|-----------|----------------| | Informational | Wikipedia, knowledge panels, "what is" queries | Learn something | Guide, tutorial, explainer | | Commercial | Reviews, comparisons, "best X" queries | Compare options | Comparison, listicle, review | | Transactional | Product pages, shopping results, "buy X" | Purchase something | Product page, pricing | | Navigational | Brand homepage, login pages | Find specific site | Homepage, login page |
| Feature | How to Identify | Optimization Strategy | |---------|-----------------|----------------------| | Featured Snippet | Box at top with answer | Direct answer in first 100 words | | People Also Ask | Expandable question boxes | FAQ section, answer common questions | | Image Pack | Row of images | High-quality images with alt text | | Video Results | YouTube thumbnails | Create video content | | Local Pack | Map with business listings | GMB optimization, location pages | | Knowledge Panel | Right sidebar info box | Schema markup, Wikipedia presence | | Sitelinks | Sub-links under main result | Clear site structure, internal linking |
| Type | Format | How to Optimize | |------|--------|-----------------| | Paragraph | Text block | 40-60 word direct answer | | List | Numbered/bulleted list | Use ordered/unordered lists | | Table | Data table | Use HTML tables | | Video | YouTube embed | Create relevant video content |
For each top 10 result, note:
| Rank | Domain | Format | Words | Unique Angle | Gap | |------|--------|--------|-------|--------------|-----| | 1 | {domain} | {format} | {count} | {angle} | {gap} | | 2 | {domain} | {format} | {count} | {angle} | {gap} | | ... | | | | | |
markdown## SERP Analysis: {keyword} ### Search Intent - **Primary Intent**: {Informational | Commercial | Transactional | Navigational} - **Confidence**: {percentage}% - **Secondary Intent**: {if mixed} ### SERP Features Present - [ ] Featured Snippet ({type}) - [ ] People Also Ask - [ ] Image Pack - [ ] Video Results - [ ] Local Pack - [ ] Knowledge Panel - [ ] Sitelinks ### Competitor Analysis | Rank | Domain | Format | Words | Unique Angle | |------|--------|--------|-------|--------------| | 1 | {domain} | {format} | {count} | {angle} | ... ### Content Gaps Identified 1. {gap} - {which competitors miss this} 2. {gap} - {which competitors miss this} ### Recommendations 1. **Content Format**: {recommended format based on SERP} 2. **Word Count**: {recommended based on competitors + 20%} 3. **Featured Snippet**: {opportunity and how to capture} 4. **Differentiator**: {unique angle to stand out}
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→pass | 11,962 | 8,912 | -25% | 1 | 1 | 0% | 1,794 | 2,349 | +31% | 0 | 0 | — |
case-01 | pass→pass | 23,060 | 12,058 | -48% | 1 | 1 | 0% | 3,949 | 2,763 | -30% | 0 | 0 | — |
case-02 | pass→pass | 7,186 | 7,988 | +11% | 1 | 1 | 0% | 1,242 | 2,374 | +91% | 0 | 0 | — |
case-03 | pass→pass | 7,636 | 6,599 | -14% | 1 | 1 | 0% | 1,634 | 2,400 | +47% | 0 | 0 | — |
case-04 | fail→fail | 22,604 | 5,394 | -76% | 1 | 1 | 0% | 3,658 | 1,273 | -65% | 0 | 0 | — |
case-05 | pass→fail | 35,444 | 4,789 | -86% | 1 | 1 | 0% | 5,511 | 1,237 | -78% | 0 | 0 | — |
case-06 | fail→fail | 27,846 | 4,539 | -84% | 1 | 1 | 0% | 4,420 | 1,275 | -71% | 0 | 0 | — |
case-07 | pass→pass | 6,967 | 4,943 | -29% | 1 | 1 | 0% | 1,063 | 1,670 | +57% | 0 | 0 | — |
case-08 | pass→pass | 9,619 | 10,292 | +7% | 1 | 1 | 0% | 1,397 | 2,483 | +78% | 0 | 0 | — |
case-09 | pass→pass | 10,046 | 9,186 | -9% | 1 | 1 | 0% | 1,437 | 2,415 | +68% | 0 | 0 | — |
case-10 | pass→pass | 4,069 | 5,607 | +38% | 1 | 1 | 0% | 610 | 1,736 | +185% | 0 | 0 | — |
case-11 | fail→fail | 17,084 | 7,531 | -56% | 1 | 1 | 0% | 2,544 | 1,288 | -49% | 0 | 0 | — |
case-12 | pass→pass | 11,511 | 27,363 | +138% | 1 | 1 | 0% | 1,756 | 2,524 | +44% | 0 | 0 | — |
case-13 | pass→fail | 12,655 | 5,897 | -53% | 1 | 1 | 0% | 1,979 | 1,246 | -37% | 0 | 0 | — |
case-14 | pass→fail | 15,596 | 4,226 | -73% | 1 | 1 | 0% | 2,331 | 1,165 | -50% | 0 | 0 | — |
case-16 | pass→fail | 15,529 | 5,122 | -67% | 1 | 1 | 0% | 2,260 | 1,153 | -49% | 0 | 0 | — |
case-17 | fail→pass | 19,098 | 11,990 | -37% | 1 | 1 | 0% | 2,832 | 2,696 | -5% | 0 | 0 | — |
case-18 | pass→pass | 10,285 | 9,265 | -10% | 1 | 1 | 0% | 1,529 | 2,337 | +53% | 0 | 0 | — |
case-19 | pass→pass | 14,924 | 11,518 | -23% | 1 | 1 | 0% | 2,141 | 2,372 | +11% | 0 | 0 | — |
case-20 | pass→pass | 15,480 | 13,979 | -10% | 1 | 1 | 0% | 2,442 | 3,304 | +35% | 0 | 0 | — |
case-21 | pass→pass | 13,743 | 7,003 | -49% | 1 | 1 | 0% | 2,072 | 2,038 | -2% | 0 | 0 | — |
case-22 | pass→pass | 11,058 | 6,397 | -42% | 1 | 1 | 0% | 1,672 | 1,966 | +18% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 15 counted toward the lift figure. The other 7 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -9 percentage points is the difference between those two pass rates over the 15 comparable cases. 6 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.